A Peer-To-Peer-based Storage Platform for Storing Session Data in Internet Access Networks
|
|
- Penelope Matthews
- 5 years ago
- Views:
Transcription
1 A Peer-To-Peer-based Storage Platform for Storing Session Data in Internet Access Networks Peter Danielis, Maik Gotzmann, Dirk Timmermann, University of Rostock Institute of Applied Microelectronics and Computer Engineering Rostock, Germany, Tel./Fax: +49 (381) / {peter.danielis;dirk.timmermann}@uni-rostock.de Thomas Bahls, Daniel Duchow, Nokia Siemens Networks GmbH & Co. KG, Broadband Access Division Greifswald, Germany, Tel./Fax: +49 (3834) / {thomas.bahls;daniel.duchow}@nsn.com Abstract Internet service providers (ISPs) have to store session data of their customers for operation, management, and control tasks. Thereby, each access node (AN) of an ISP s access network keeps track of session data (e.g., IP addresses, MAC addresses, and lease times of IP addresses) of all connected customers. Session data is highly volatile due to continuous changes. It has to be stored persistently as it is required for regular data forwarding and traffic filtering. In case of an AN s restart or crash, it needs to be reloaded. Today, session data is stored in an AN s flash memory, which is limited in its availability and rewritability and intended for other purposes. Therefore, this paper proposes to organize ANs into a distributed hash table (DHT)-based Peer-to-Peer network to share their available RAM resources. Thereby, the DHT network serves as semi-permanent distributed memory for a structured redundant and interleaved storage of session data. In doing so, availability of session data is actually increased despite using RAM for data storage. After a restart or crash, an AN reloads session data by selectively reading required data from the DHT network. 1 Introduction Internet service providers (ISPs) have to store session data of their customers as it is required for operation, management, and control tasks. Thereby, each access node (AN), e.g., a DSLAM (Digital Subscriber Line Access Multiplexer), a CMTS (Cable Modem Termination System), or a GPON OLT (Gigabit Passive Optical Network Optical Line Termination) of an ISP s access network keeps track of session data of all customers, which are connected to it via physical ports. Session data comprises, among other things, address information such as IP addresses, physical ports, MAC addresses, and lease times of IP addresses. The data is highly volatile due to continuous changes of its database requiring frequent memory accesses for rewriting. A customer connecting to the Internet automatically requests an IP address via DHCP. Session data has to be stored persistently and is accessed on a regular base for regular data forwarding as well as for traffic filters restricting traffic based on configured address information. In case of an AN s restart or crash, data has to be reloaded, i.e., session data recovery is needed. Today, flash memory is used to assure persistency of session data. However, this memory is limited in its availability and rewritability and is intended for other purposes such as the storage of configuration parameters of an AN. In addition to flash memory, ANs have a certain available volatile RAM storage and computing capacity, which may be used at no extra costs. In contrast to flash memory, RAM memory can be rewritten almost unlimited. Therefore, this paper proposes to organize ANs into a distributed hash table (DHT)-based Peer-to-Peer (P2P) network to share their available RAM resources. Thereby, the DHT network serves as semi-permanent distributed memory for a structured storage of session data. Each AN contributes a part of its storage and computing capacity to the DHT network. After a restart or crash, an AN performs session data recovery by selectively reading required data from the DHT network so that persistency is assured. Session data has to be available with a very high reliability, typically with a probability of at least %, often refered to as five nines. As data is stored in a distributed manner on all ANs, this availability has to be ensured by adequate mechanisms as ANs may fail or be unavailable. Therefore, data is stored redundantly. To keep this redundancy at a minimum while providing a high availability, erasure resilient codes are explored and compared to simple data replication [1]. Briefly summarized, the main contributions of this paper are the following: Options offered by P2P technology for designing a decentralized storage platform in the access network are investigated. P2P technology is used to realize semi-permanent storage of session data in volatile RAM memory. A P2P system for the realization of the P2P-based storage platform is chosen. Erasure resilient codes and simple data replication
2 are compared regarding data availability and storage overhead. An erasure resilient code is chosen and implemented. Architecture and functionality of the P2P-based storage platform (PSP) are described. The remainder of this paper is organized as follows: Section 2 describes how to utilize P2P technology for realizing a distributed storage platform. Section 3 explains how to achieve high data availability for PSP. Section 4 presents the realization of PSP. Section 5 contains a comparison with related work. The paper concludes in Section 6. 2 Utilizing P2P Technology for a Decentralized Storage Platform To avoid the utilization of flash memory for centralized session data storage, a decentralized storage solution is desirable where available resources can be used. Thereby, ANs, which are located in the access area (see Figure 1), shall serve as platform for such a solution. Each AN has a unique ID, which may be an alphanumeric string. Customers Area Customers Access Area Flash Memory with Session Data Access Node, e.g., DSL Access Multiplexer Core Network Area Internet Service Provider Broadband Remote Access Server Internet Figure 1: Access network containing ANs. Today, session data for connected customers is stored in the flash memory of each AN and requested via DHCP. P2P technology offers many promising options to efficiently realize such a decentralized solution. Beyond its incriminated applications like, e.g., file sharing, P2P is a new networking paradigm. No clients and servers exist. All network nodes are peers, i.e., ANs are both client and server and form a logical overlay on top of the existing topology. Thereby, scalability and resilience are intrinsic features of P2P. There is no single point of failure in a P2P network. Therefore, it inherently provides high resilience towards DoS attacks and network faults. Moreover, it is a proven concept as it has been successfully applied in, e.g., recently developed P2P-based IPTV solutions like Zattoo and Joost [2, 3]. Each AN contributes to the P2P-based network application with its available resources. Thus, the P2P network itself is a distributed storage resource with ANs sharing their available memory. Thereby, each AN stores just a fragment of all session data. ANs share their computational power. Thus, the network is also a distributed computing resource. A wide variety of P2P systems and alternatives exist, e.g., unstructured decentralized systems like Gnutella and structured DHT-based systems like Kademlia [4]. DHTs are chosen as they offer the best trade-off between search and storage complexity [4]. DHTs are self-organizing, i.e., no external maintenance is necessary. DHTs allow for deterministic lookups to avoid false negatives. Most DHT-based P2P networks support redundant data storage. This property contributes to an even higher resilience as session data is available on the DHT ring with a high probability even in case of one or more failing ANs. 2.1 Choosing a DHT-based P2P Protocol There are manifold DHT-based P2P protocols such as, e.g., Chord, Pastry, and Kademlia [5, 6, 7]. Most of them have a logarithmic search complexity. Each DHT-based protocol provides for a routing table, which contains contacts for lookups. By reason of its flexibility of the routing table and high lookup performance as well as its analysis properties, the Kademlia protocol has been selected. Kademlia s advantageous analysis properties allow for an easy formal analysis of its worst-case behavior. Its flexibility of the routing table allows for a high lookup performance by using temporary contacts and keeps efforts for the maintenance at a minimum. For the realization of PSP, the Kademlia-based Kad protocol is chosen, which has been implemented and applied in the emule client [8]. 2.2 The Kademlia-based P2P Protocol Kad To each peer, which is part of the Kad network, a hash value is assigned (e.g., 16 bytes calculated by MD5). Based on its hash value, a peer occupies a place in the hash address space. Based on an identifier of a fragment of session data (called chunk), a hash value from the same address space is calculated. This identifier may be the concatenation of an AN s ID and the file name of the chunk. A peer stores session data chunks with hash values similar to its own hash value. The distance needed to derive the similarity degree between two hash values is calculated by the XOR metric. Two hash values are similar if their distance is not greater then a defined search tolerance. Peers always have sufficient information about other peers in their direct neighborhood. In distant regions, they always know at least one contact or more due to the flexibility of the routing table. This guarantees low latency for lookups as requests can be issued in parallel and delays caused by failing peers can be avoided. An iterative algorithm is applied for lookups on the DHT ring. During a lookup, the searching peer first contacts peers, which are closest to the hash value of the requested part of session data, from its own routing table. In return, those peers answer the searching peer. Thereby, it learns new contacts until it knows contacts with sufficiently similar hash values. The lookup algorithm is simplified by using the XOR metric as it makes the Kad network more consistent and more efficient [8].
3 For the use with PSP, the Kad protocol has been modified to convey session data and extended with a deletion functionality to erase session data chunks. 3 Achieving High Data Availability The most important and decisive criterion for the storage of data in general and session data in particular is to ensure high data availability [1]. Especially in case of distributed storage, appropriate measures have to be taken to reach a data availability P d of typically at least %. On the one hand, a high value for P d can be assured by data replication. On the other hand, data can be split into data chunks and redundancy is added in the form of interleaved coding chunks (erasure resilient coding). Data and its replicas or data chunks and coding chunks are saved on several storage systems, i.e., ANs in the authors envisaged use case. Node availability P n is constant as it can only be improved by the deployment of more reliable hardware. Therefore, data availability P d can only be increased by adding redundancy. Consequently, the data volume to be stored is increased. This is considered as costs for higher data availability and shall be referred to as storage overhead factor S. Thereby, S denotes the ratio of original data volume + added redundancy divided by original data volume. As storage capacity of ANs is limited, S should be as small as possible while providing high data availability P d. To find out the best candidate for satisfying this requirement, simple data replication is compared to erasure resilient coding in terms of S and P d in the following. 3.1 Simple Data Replication vs. Erasure Resilient Coding In case of simple data replication (DR), data is copied from the node holding it to S - 1 other nodes. Thereby, S is an integer value as complete data copies are generated. To restore the original data after a restart or crash, it has to be copied back from one of these S - 1 nodes. Consequently, P d depends on P n and S [1]: P d, DR = S 1 ( ) S 1 P i i n(1 P n ) S 1 i (1) i=1 If using erasure resilient coding (ERC) data has to be split into m data chunks before storage. Then, k coding chunks are created containing information of all m data chunks. Thus, n = m + k chunks are generated, which represent the data. From any m of these n chunks, an efficient erasure resilient code is able to restore the original data. Thus, P d depends on P n, m, and n whereby n/m = S [1]: P d, ERC = n i=m ( ) n P i i n(1 P n ) n i (2) Basically, both DR and ERC increase data availability. However, ERC provides a desired data availability P d with much less storage overhead than DR. Let P d be % and a node be available with P n = 90 %. Using DR, a value of 6 is obtained for S from Equation 1, i.e., data would have to be replicated five times. Contrary, ERC provides P d = % with a much lower S = 2 (with, e.g., n = 32 and m = 16). Thus, ERC decreases S by a factor of three. Consequently, ERC is used for ensuring high data availability rather than simple data replication. ERC shows high complexity regarding the generation of coding chunks and for decoding them into a complete file if necessary. Anyway, ANs have sufficient computing power available for solving this computational task. 3.2 Reed-Solomon Codes Reed-Solomon (RS) codes are chosen as erasure resilient code as they are very practical for achieving high availability for distributed storage [9]. One advantages is their capability of restoring data from exactly m arbitrary data chunks. Thus, RS codes optimally exploit added redundancy. Another advantage results from the property of RS codes to be systematic block codes. This means that data and coding chunks are ordered. Thereby, data chunks are followed by coding chunks. If m of n chunks are available and if these are data chunks, data can be restored by simple reassembly of them without decoding. This makes RS codes very efficient and saves computing time and power for decoding. 4 Kad-based Realization of PSP PSP is realized by organizing an ISP s ANs into a Kadbased DHT. These ANs save session data chunks of other PSP nodes in a structured way (see Figure 2). Session data chunks include chunks session data has been split into and coding chunks generated by means of the RS code. As an AN represents a peer, i.e., a PSP node in the Kad network, a hash value is assigned to it, e.g., calculated from its IP address. Based on its hash value, an AN inserts itself on the DHT ring, which covers the whole hash address space. Thereby, each AN stores its own session data in its RAM to be able to provide connected customers with IP addresses. is responsible for storing session data chunks with similar hash values calculated from a concatenation of AN ID and the file name of the session data chunks. As proof of concept, a prototype has been developed, which emulates an AN with PSP functionality. It is implemented in C++ and currently runs under Windows. 4.1 Architecture of a PSP Node The design of a PSP node is depicted in Figure 3. The main components are the memory with own session data (1), a memory with session data chunks of other PSP nodes (2), a
4 Chunk of AN 2 Chunk of AN 3 AN 4 Chunk of AN 2 Chunk of AN 3 Access Node (AN) 1 Logical P2P network on top of real topology: Kad-based DHT ring AN 2 Chunk of AN 1 Chunk of AN 2 AN 3 Chunk of AN 1 Chunk of AN 4 Chunk of AN 4 Figure 2: Kad-based DHT ring for structured storage of session data chunks. routing table (3), the Kad block (4), and a module with functionality to process triggers (5). The memory with own session data provides session data for customers directly connected to the AN. The second memory stores session data chunks, which the PSP node is responsible for, based on its hash value. The routing table contains contact information about other PSP nodes to be able to communicate with them. The Kad block realizes the functionality of the Kad protocol. This includes bootstrapping, maintenance, and the execution of lookups and store and delete operations on the Kad-based DHT ring. It should be noted that at least one PSP node is assumed to be always available in the Kad network to be used for bootstrapping by joining nodes. Furthermore, the Kad block contains RS functionality to split and code session data into chunks and and vice versa to decode chunks into session data. These chunks are transfered via TCP in case of a lookup or a store operation on the Kad ring. If a PSP node shall execute an operation on the DHT ring, the Kad block is advised to contact PSP nodes from its routing table. A predefined number of PSP nodes closest to the hash value of a session data chunk is contacted in parallel. 4.2 PSP Node Activities PSP node activities can be triggered by internal and external triggers. The node reacting on a trigger and executing an operation is called triggering node. Internal triggers are caused by internal processes such as a change or the loss of the session data on an AN. External triggers can be received via an interfaces to the ISP, i.e., to an administrator (see Figure 4). Via this interface, lookups, store and delete, and configuration requests are issued and an (un-)successful processing is signaled. These requests can be either sent via packets or issued through an API between administrator and PSP node functionality. This interface allows for a flexible access to and configuration of an AN s session data by an administrative instance. Via the interface to the Kad-based DHT ring, Kad requests and responses are received and sent, which are used for lookups and store and delete operations on the DHT ring. Packets for bootstrapping and maintenance are exchanged via this interface as well. Moreover, TCP data transfer of session data chunks is performed here. Following, internal and external triggers and the interaction with other PSP nodes are described in detail Internal Triggers on a PSP Node Internal triggers indicate when session data of an AN has to be read (lookup) or deleted from the DHT ring or stored. If an AN is restarted after a crash or reset a lookup is automatically triggered on the Kad ring. Thereby, the restarted AN reads back its own session data by requesting appropriate chunks from other nodes. As session data is stored in the AN s RAM, it is lost after restart and therefore needs to be restored. If an AN notices changes in its session data it initiates a delete operation on the DHT ring. Thereby, it deletes session data chunks created from the old session data. Changes can occur due to expired leases times of IP addresses or customers releasing their IP address (DHCP release) and administrative changes in the configuration of session data. After an AN noticed changes in in its session data and deleted appropriate session data chunks from the DHT ring, session data chunks are created from the new session data and stored on the DHT ring External Triggers from an Administrator External trigger requests may only be sent by an administrative instance of the ISP. These messages are intended to explicitly request (lookup), store, or delete session data chunks if an AN s session data has been modified or shall be restored. Furthermore, parameters of the RS code can be configured to achieve desired data availability P d (configuration request). If a PSP node receives a search request from the administrator a lookup on the DHT ring is initiated. After a successful lookup, a search response is sent back to the adminis-
5 To ISP (Administrator) External Trigger Responses Own Session Data 1 2 (of other Nodes) Routing Table 3 To Kad Module for processing triggers 5 Operation Kad functionality 4 Reed- Solomon (De-)Coding TCP functionality From Kad Result from Kad Lookup External Trigger Requests From ISP (Administrator) Figure 3: Block diagram of a PSP node. trator signaling an (un-)successful processing of the search request. PSP nodes Kad based DHT ring Operation (Kad Request/ Response) Internal Triggers Triggering PSP Node External Trigger Requests/ Responses ISP (Administrator) Figure 4: External and internal triggers leading to node activity and interactions with other PSP nodes. If a node receives an update request, it splits its session data into chunks and generates coding chunks by means of the RS code. Then, a store operation on the DHT ring is initiated. Finally, the node responds with an update response. On reception of a delete request, a delete operation on the DHT ring is initiated and a delete response is sent back. Moreover, an administrator can trigger the deletion of an AN s memory holding its own session data (delete memory request). In this case, session data chunks are not deleted from the DHT ring. It may be necessary to delete an AN s own session data to undo changes and then restore the original session data from the DHT ring Interactions with other PSP Nodes Lookups on the DHT ring: Lookups are initiated by search requests from the administrator or internal triggers. During a lookup, nodes are contacted, which are closest to the hash value of the requested session data chunks. First, these contacts are taken from the routing table of the triggering node. In the course of the lookup, closer nodes are learnt from the responses of contacted nodes. Finally, nodes with a hash value similar to the hash value (within the search tolerance) of the requested session data chunks are found and contacted. Such a node tries to find session data chunks in its memory. If it succeeds it answers the triggering PSP node, which immediately terminates the lookup. If the requested session data chunks can not be found on any node, a timeout terminates the lookup. As RS codes are used to ensure high data availability P d, the probability for not finding session data chunks on any PSP node is 1-P d. Thus, timeouts terminating a lookup should rarely occur. Store operations on the DHT ring: Store operations are initiated by update requests from the administrator or internal triggers. In the same way, a lookup is done, close nodes from the routing table of the triggering node are contacted first. When sufficiently close nodes have been learnt, they are advised to store the session data chunks. The store operation terminates if all session data chunks have been stored or through a timeout. A timeout may only occur if the store operation fails for any chunk. In this case, the operation is repeated until it is successful. Delete operations on the DHT ring: Delete operations are initiated by update delete requests from the administrator or internal triggers. They work like lookups and store operations. Sufficiently close nodes are advised to delete the session data chunks. The delete operation terminates if all nodes have deleted the session data chunks or through a timeout. A timeout should only occur if one of the nodes holding a session data chunk to delete has gone offline. Any of the operations contribute to increase the number of contacts the triggering node knows. Thereby, the Kad network becomes more redundant and more robust. Also, the lookup performance potentially increases as some iteration steps on the way to the target may be left out because closer contacts have been learnt. 4.3 Related Issues Session data has memory requirements of some MBytes per AN. Therefore, the quantitative amount of memory that can
6 be saved by using ERC compared to replicating data is moderate (given a desired data availability). However, vice versa a significantly higher data availability can be assured by ERC in any case (given a certain available memory capacity). The utilization of the Kad network introduces some restrictions on PSP. As it bases on open source code of the emule client, the exploitation of flaws by hackers is theoretically simplified. However, open source-based Apache web servers are market leader and Linux continuously increases its market shares, which argues for the high quality of open source code [10]. Communication in the Kad network introduces additional traffic into the network. But due to Kad s flexible routing table, traffic overhead through maintenance is minimal. 5 State-of-the-art in P2P-based Storage Platforms [11, 12, 13] propose to use DHT-based solutions for distributed storage of data. In [11], globally distributed untrusted servers shall be used. In [12], the authors suggest a public data management system for Web applications. The solution in [13] focuses on a scalable storage platform for storing IP flow records. In [14], data sets are organized into redundancy groups. Thereby, the focus is on high availability of data in P2P-based applications with a high churn of nodes. In contrast to the author s approach, none of the cited works uses available resources of trusted reliable infrastructure to provide a storage platform for general data. 6 Conclusion This paper proposes a P2P-based storage platform called PSP, which supersedes the use of expensive and rarely available flash memory for storing session data. Instead, available RAM storage and computing capacity of ANs is utilized, assuming some idle time or spare capacity being left in an average AN. In that way, the storage of session data is provided without additional costs for the ISP. Via the DHTbased P2P network Kad, ANs are organized into a logical P2P overlay on top of the existing topology. Thereby, they share their available memory and computing resources. As high scalability and resilience are intrinsic features of DHTs, PSP shows these features at no extra costs. As session data is stored interleaved by means of erasure resilient codes, all data can be restored even in case of a high number of unavailable ANs. Thereby, much less storage overhead is created than using simple data replication. As proof of concept, a software prototype has been developed, which emulates an AN with PSP functionality. Currently, this prototype is ported to a Xilinx evaluation board. Acknowledgement The authors would like to thank the Broadband Access Division of Nokia Siemens Networks GmbH & Co. KG in Greifswald, Germany for their inspiration and continued support in this project. This work is partly granted by Nokia Siemens Networks. References [1] W.K. Lin et al., Erasure Code Replication Revisited. IEEE P2P, 2004, pp [2] Joost - Free Online TV, [Online]. Available: [3] Zattoo - TV to Go, [Online]. Available: [4] R. Steinmetz and K. Wehrle, P2P Systems and Applications, Springer Lecture Notes in Computer Science. Springer-Verlag Berlin Heidelberg, [5] Ion Stoica et al., Chord: A Scalable Peer-to-peer Lookup Service for Internet Applications. ACM SIGCOMM, 2001, pp [6] A. Rowstron and P. Druschel, Pastry: Scalable, Decentralized Object Location, and Routing for Large- Scale Peer-to-Peer Systems. 18th IFIP/ACM International Conference on Distributed Systems Platforms, 2001, pp [7] P. Maymounkov and D. Mazieres, Kademlia: A peerto-peer information system based on the xor metric. IPTPS02, Cambridge, USA March [8] R. Brunner, A performance evaluation of the Kadprotocol, Master s thesis, University of Mannheim, Germany, November [9] W. C. Huffman and V. Pless, Fundamentals of Error- Correcting Codes. Cambridge University Press, [10] NETCRAFT, August 2009 Web Server Survey, August [Online]. Available: http: //news.netcraft.com/archives/web_server_survey.html [11] J. Kubiatowicz et al., OceanStore: An Architecture for Global-Scale Persistent Storage. ASPLOS, 2000, pp [12] M. Karnstedt et al., UniStore: Querying a DHT-based Universal Storage. International Conference on Data Engineering, 2007, pp [13] C. Morariu et al., DIPStorage: Distributed Storage of IP Flow Records. 16th IEEE LANMAN, 2008, pp [14] Qin Xin et al., Availability in Global Peer-To-Peer Storage Systems. Distributed Data and Structures, Proceedings in Informatics, 2004.
Dynamic Search Tolerance at Runtime for Lookup Determinism in the DHT-based P2P Network Kad
Dynamic Search Tolerance at Runtime for Lookup Determinism in the DHT-based P2P Network Kad Peter Danielis, Jan Skodzik, Vlado Altmann, Lennard Lender, Dirk Timmermann University of Rostock Institute of
More informationArchitectures for Distributed Systems
Distributed Systems and Middleware 2013 2: Architectures Architectures for Distributed Systems Components A distributed system consists of components Each component has well-defined interface, can be replaced
More informationProblems in Reputation based Methods in P2P Networks
WDS'08 Proceedings of Contributed Papers, Part I, 235 239, 2008. ISBN 978-80-7378-065-4 MATFYZPRESS Problems in Reputation based Methods in P2P Networks M. Novotný Charles University, Faculty of Mathematics
More informationAthens University of Economics and Business. Dept. of Informatics
Athens University of Economics and Business Athens University of Economics and Business Dept. of Informatics B.Sc. Thesis Project report: Implementation of the PASTRY Distributed Hash Table lookup service
More informationMarch 10, Distributed Hash-based Lookup. for Peer-to-Peer Systems. Sandeep Shelke Shrirang Shirodkar MTech I CSE
for for March 10, 2006 Agenda for Peer-to-Peer Sytems Initial approaches to Their Limitations CAN - Applications of CAN Design Details Benefits for Distributed and a decentralized architecture No centralized
More informationSurvey of DHT Evaluation Methods
Survey of DHT Evaluation Methods Markus Meriläinen Helsinki University of Technology Markus.Merilainen@tkk.fi Abstract In this paper, we present an overview of factors affecting the performance of the
More informationL3S Research Center, University of Hannover
, University of Hannover Dynamics of Wolf-Tilo Balke and Wolf Siberski 21.11.2007 *Original slides provided by S. Rieche, H. Niedermayer, S. Götz, K. Wehrle (University of Tübingen) and A. Datta, K. Aberer
More informationLecture 6: Overlay Networks. CS 598: Advanced Internetworking Matthew Caesar February 15, 2011
Lecture 6: Overlay Networks CS 598: Advanced Internetworking Matthew Caesar February 15, 2011 1 Overlay networks: Motivations Protocol changes in the network happen very slowly Why? Internet is shared
More informationAn Empirical Study of Data Redundancy for High Availability in Large Overlay Networks
An Empirical Study of Data Redundancy for High Availability in Large Overlay Networks Giovanni Chiola Dipartimento di Informatica e Scienze dell Informazione (DISI) Università di Genova, 35 via Dodecaneso,
More informationACIP: An Access Control and Information Protocol for Ethernet-based Broadband Access Networks
ACIP: An Access Control and Information Protocol for Ethernet-based Broadband Access Networks Daniel Duchow and Dirk Timmermann University of Rostock, 18051 Rostock, Germany Tel/Fax: ++49 381 498-7276/52
More informationKademlia: A P2P Informa2on System Based on the XOR Metric
Kademlia: A P2P Informa2on System Based on the XOR Metric Today! By Petar Mayamounkov and David Mazières, presented at IPTPS 22 Next! Paper presentation and discussion Image from http://www.vs.inf.ethz.ch/about/zeit.jpg
More informationBitTorrent. Masood Khosroshahy. July Tech. Report. Copyright 2009 Masood Khosroshahy, All rights reserved.
BitTorrent Masood Khosroshahy July 2009 Tech. Report Copyright 2009 Masood Khosroshahy, All rights reserved. www.masoodkh.com Contents Contents 1 Basic Concepts 1 2 Mechanics 3 2.1 Protocols: Tracker and
More informationScalability In Peer-to-Peer Systems. Presented by Stavros Nikolaou
Scalability In Peer-to-Peer Systems Presented by Stavros Nikolaou Background on Peer-to-Peer Systems Definition: Distributed systems/applications featuring: No centralized control, no hierarchical organization
More informationDistributed Hash Table
Distributed Hash Table P2P Routing and Searching Algorithms Ruixuan Li College of Computer Science, HUST rxli@public.wh.hb.cn http://idc.hust.edu.cn/~rxli/ In Courtesy of Xiaodong Zhang, Ohio State Univ
More informationDYNAMIC TREE-LIKE STRUCTURES IN P2P-NETWORKS
DYNAMIC TREE-LIKE STRUCTURES IN P2P-NETWORKS Herwig Unger Markus Wulff Department of Computer Science University of Rostock D-1851 Rostock, Germany {hunger,mwulff}@informatik.uni-rostock.de KEYWORDS P2P,
More informationTime Synchronization in the DHT-based P2P Network Kad for Real-Time Automation Scenarios
Time Synchronization in the DHT-based PP Network Kad for Real-Time Automation Scenarios Jan Skodzik, Peter Danielis, Vlado Altmann, Dirk Timmermann University of Rostock Institute of Applied Microelectronics
More informationSearching for Shared Resources: DHT in General
1 ELT-53207 P2P & IoT Systems Searching for Shared Resources: DHT in General Mathieu Devos Tampere University of Technology Department of Electronics and Communications Engineering Based on the original
More informationSearching for Shared Resources: DHT in General
1 ELT-53206 Peer-to-Peer Networks Searching for Shared Resources: DHT in General Mathieu Devos Tampere University of Technology Department of Electronics and Communications Engineering Based on the original
More informationCS555: Distributed Systems [Fall 2017] Dept. Of Computer Science, Colorado State University
CS 555: DISTRIBUTED SYSTEMS [P2P SYSTEMS] Shrideep Pallickara Computer Science Colorado State University Frequently asked questions from the previous class survey Byzantine failures vs malicious nodes
More informationOverlay networks. To do. Overlay networks. P2P evolution DHTs in general, Chord and Kademlia. Turtles all the way down. q q q
Overlay networks To do q q q Overlay networks P2P evolution DHTs in general, Chord and Kademlia Turtles all the way down Overlay networks virtual networks Different applications with a wide range of needs
More informationPeer-to-Peer Systems and Distributed Hash Tables
Peer-to-Peer Systems and Distributed Hash Tables CS 240: Computing Systems and Concurrency Lecture 8 Marco Canini Credits: Michael Freedman and Kyle Jamieson developed much of the original material. Selected
More informationR/Kademlia: Recursive and Topology-aware Overlay Routing
R/Kademlia: Recursive and Topology-aware Overlay Routing Bernhard Heep ATNAC 2010, Auckland, New Zealand, 11/02/2010, KIT University of the State of Baden-Wuerttemberg and National Research Center of the
More informationChapter 10: Peer-to-Peer Systems
Chapter 10: Peer-to-Peer Systems From Coulouris, Dollimore and Kindberg Distributed Systems: Concepts and Design Edition 4, Addison-Wesley 2005 Introduction To enable the sharing of data and resources
More informationDesign of a New Hierarchical Structured Peer-to-Peer Network Based On Chinese Remainder Theorem
Design of a New Hierarchical Structured Peer-to-Peer Network Based On Chinese Remainder Theorem Bidyut Gupta, Nick Rahimi, Henry Hexmoor, and Koushik Maddali Department of Computer Science Southern Illinois
More informationTelecommunication Services Engineering Lab. Roch H. Glitho
1 Support Infrastructure Support infrastructure for application layer Why? Re-usability across application layer protocols Modularity (i.e. separation between application layer protocol specification /
More informationPeer-to-Peer Systems. Chapter General Characteristics
Chapter 2 Peer-to-Peer Systems Abstract In this chapter, a basic overview is given of P2P systems, architectures, and search strategies in P2P systems. More specific concepts that are outlined include
More informationA Framework for Peer-To-Peer Lookup Services based on k-ary search
A Framework for Peer-To-Peer Lookup Services based on k-ary search Sameh El-Ansary Swedish Institute of Computer Science Kista, Sweden Luc Onana Alima Department of Microelectronics and Information Technology
More informationBuilding a low-latency, proximity-aware DHT-based P2P network
Building a low-latency, proximity-aware DHT-based P2P network Ngoc Ben DANG, Son Tung VU, Hoai Son NGUYEN Department of Computer network College of Technology, Vietnam National University, Hanoi 144 Xuan
More informationA Directed-multicast Routing Approach with Path Replication in Content Addressable Network
2010 Second International Conference on Communication Software and Networks A Directed-multicast Routing Approach with Path Replication in Content Addressable Network Wenbo Shen, Weizhe Zhang, Hongli Zhang,
More informationA Structured Overlay for Non-uniform Node Identifier Distribution Based on Flexible Routing Tables
A Structured Overlay for Non-uniform Node Identifier Distribution Based on Flexible Routing Tables Takehiro Miyao, Hiroya Nagao, Kazuyuki Shudo Tokyo Institute of Technology 2-12-1 Ookayama, Meguro-ku,
More informationA Chord-Based Novel Mobile Peer-to-Peer File Sharing Protocol
A Chord-Based Novel Mobile Peer-to-Peer File Sharing Protocol Min Li 1, Enhong Chen 1, and Phillip C-y Sheu 2 1 Department of Computer Science and Technology, University of Science and Technology of China,
More informationIntroduction to Peer-to-Peer Systems
Introduction Introduction to Peer-to-Peer Systems Peer-to-peer (PP) systems have become extremely popular and contribute to vast amounts of Internet traffic PP basic definition: A PP system is a distributed
More informationPeer-to-peer systems and overlay networks
Complex Adaptive Systems C.d.L. Informatica Università di Bologna Peer-to-peer systems and overlay networks Fabio Picconi Dipartimento di Scienze dell Informazione 1 Outline Introduction to P2P systems
More informationA Top Catching Scheme Consistency Controlling in Hybrid P2P Network
A Top Catching Scheme Consistency Controlling in Hybrid P2P Network V. Asha*1, P Ramesh Babu*2 M.Tech (CSE) Student Department of CSE, Priyadarshini Institute of Technology & Science, Chintalapudi, Guntur(Dist),
More informationA Hybrid Peer-to-Peer Architecture for Global Geospatial Web Service Discovery
A Hybrid Peer-to-Peer Architecture for Global Geospatial Web Service Discovery Shawn Chen 1, Steve Liang 2 1 Geomatics, University of Calgary, hschen@ucalgary.ca 2 Geomatics, University of Calgary, steve.liang@ucalgary.ca
More informationPeer to Peer Networks
Sungkyunkwan University Peer to Peer Networks Prepared by T. Le-Duc and H. Choo Copyright 2000-2017 Networking Laboratory Presentation Outline 2.1 Introduction 2.2 Client-Server Paradigm 2.3 Peer-To-Peer
More informationPeer-to-Peer Systems. Network Science: Introduction. P2P History: P2P History: 1999 today
Network Science: Peer-to-Peer Systems Ozalp Babaoglu Dipartimento di Informatica Scienza e Ingegneria Università di Bologna www.cs.unibo.it/babaoglu/ Introduction Peer-to-peer (PP) systems have become
More informationGNUnet Distributed Data Storage
GNUnet Distributed Data Storage DHT and Distance Vector Transport Nathan S. Evans 1 1 Technische Universität München Department of Computer Science Network Architectures and Services July, 24 2010 Overview
More informationDistributed Knowledge Organization and Peer-to-Peer Networks
Knowledge Organization and Peer-to-Peer Networks Klaus Wehrle Group Chair of Computer Science IV RWTH Aachen University http://ds.cs.rwth-aachen.de 1 Organization of Information Essential challenge in?
More informationSimulations of Chord and Freenet Peer-to-Peer Networking Protocols Mid-Term Report
Simulations of Chord and Freenet Peer-to-Peer Networking Protocols Mid-Term Report Computer Communications and Networking (SC 546) Professor D. Starobinksi Brian Mitchell U09-62-9095 James Nunan U38-03-0277
More informationEffects of Churn on Structured P2P Overlay Networks
International Conference on Automation, Control, Engineering and Computer Science (ACECS'14) Proceedings - Copyright IPCO-214, pp.164-17 ISSN 2356-568 Effects of Churn on Structured P2P Overlay Networks
More informationSlides for Chapter 10: Peer-to-Peer Systems
Slides for Chapter 10: Peer-to-Peer Systems From Coulouris, Dollimore, Kindberg and Blair Distributed Systems: Concepts and Design Edition 5, Addison-Wesley 2012 Overview of Chapter Introduction Napster
More informationMULTI-DOMAIN VoIP PEERING USING OVERLAY NETWORK
116 MULTI-DOMAIN VoIP PEERING USING OVERLAY NETWORK Herry Imanta Sitepu, Carmadi Machbub, Armein Z. R. Langi, Suhono Harso Supangkat School of Electrical Engineering and Informatics, Institut Teknologi
More informationL3S Research Center, University of Hannover
, University of Hannover Structured Peer-to to-peer Networks Wolf-Tilo Balke and Wolf Siberski 3..6 *Original slides provided by K. Wehrle, S. Götz, S. Rieche (University of Tübingen) Peer-to-Peer Systems
More informationOverview Computer Networking Lecture 16: Delivering Content: Peer to Peer and CDNs Peter Steenkiste
Overview 5-44 5-44 Computer Networking 5-64 Lecture 6: Delivering Content: Peer to Peer and CDNs Peter Steenkiste Web Consistent hashing Peer-to-peer Motivation Architectures Discussion CDN Video Fall
More informationToday. Why might P2P be a win? What is a Peer-to-Peer (P2P) system? Peer-to-Peer Systems and Distributed Hash Tables
Peer-to-Peer Systems and Distributed Hash Tables COS 418: Distributed Systems Lecture 7 Today 1. Peer-to-Peer Systems Napster, Gnutella, BitTorrent, challenges 2. Distributed Hash Tables 3. The Chord Lookup
More informationIntroduction to Peer-to-Peer Networks
Introduction to Peer-to-Peer Networks The Story of Peer-to-Peer The Nature of Peer-to-Peer: Generals & Paradigms Unstructured Peer-to-Peer Systems Sample Applications 1 Prof. Dr. Thomas Schmidt http:/www.informatik.haw-hamburg.de/~schmidt
More informationDRing: A Layered Scheme for Range Queries over DHTs
DRing: A Layered Scheme for Range Queries over DHTs Nicolas Hidalgo, Erika Rosas, Luciana Arantes, Olivier Marin, Pierre Sens and Xavier Bonnaire Université Pierre et Marie Curie, CNRS INRIA - REGAL, Paris,
More informationDepartment of Computer Science Institute for System Architecture, Chair for Computer Networks. File Sharing
Department of Computer Science Institute for System Architecture, Chair for Computer Networks File Sharing What is file sharing? File sharing is the practice of making files available for other users to
More informationProviding File Services using a Distributed Hash Table
Providing File Services using a Distributed Hash Table Lars Seipel, Alois Schuette University of Applied Sciences Darmstadt, Department of Computer Science, Schoefferstr. 8a, 64295 Darmstadt, Germany lars.seipel@stud.h-da.de
More informationPeer-to-peer computing research a fad?
Peer-to-peer computing research a fad? Frans Kaashoek kaashoek@lcs.mit.edu NSF Project IRIS http://www.project-iris.net Berkeley, ICSI, MIT, NYU, Rice What is a P2P system? Node Node Node Internet Node
More informationDistributed Hash Tables
Distributed Hash Tables CS6450: Distributed Systems Lecture 11 Ryan Stutsman Material taken/derived from Princeton COS-418 materials created by Michael Freedman and Kyle Jamieson at Princeton University.
More informationA Super-Peer Based Lookup in Structured Peer-to-Peer Systems
A Super-Peer Based Lookup in Structured Peer-to-Peer Systems Yingwu Zhu Honghao Wang Yiming Hu ECECS Department ECECS Department ECECS Department University of Cincinnati University of Cincinnati University
More informationOverlay and P2P Networks. Structured Networks and DHTs. Prof. Sasu Tarkoma
Overlay and P2P Networks Structured Networks and DHTs Prof. Sasu Tarkoma 6.2.2014 Contents Today Semantic free indexing Consistent Hashing Distributed Hash Tables (DHTs) Thursday (Dr. Samu Varjonen) DHTs
More informationLECT-05, S-1 FP2P, Javed I.
A Course on Foundations of Peer-to-Peer Systems & Applications LECT-, S- FPP, javed@kent.edu Javed I. Khan@8 CS /99 Foundation of Peer-to-Peer Applications & Systems Kent State University Dept. of Computer
More informationTinyTorrent: Implementing a Kademlia Based DHT for File Sharing
1 TinyTorrent: Implementing a Kademlia Based DHT for File Sharing A CS244B Project Report By Sierra Kaplan-Nelson, Jestin Ma, Jake Rachleff {sierrakn, jestinm, jakerach}@cs.stanford.edu Abstract We implemented
More informationPeer-To-Peer Techniques
PG DynaSearch Markus Benter 31th October, 2013 Introduction Centralized P2P-Networks Unstructured P2P-Networks Structured P2P-Networks Misc 1 What is a Peer-to-Peer System? Definition Peer-to-peer systems
More informationDistributed Information Processing
Distributed Information Processing 14 th Lecture Eom, Hyeonsang ( 엄현상 ) Department of Computer Science & Engineering Seoul National University Copyrights 2016 Eom, Hyeonsang All Rights Reserved Outline
More informationPeer to Peer Networks
Sungkyunkwan University Peer to Peer Networks Prepared by T. Le-Duc and H. Choo Copyright 2000-2018 Networking Laboratory P2P Applications Traditional P2P applications: for file sharing BitTorrent, Emule
More informationEarly Measurements of a Cluster-based Architecture for P2P Systems
Early Measurements of a Cluster-based Architecture for P2P Systems Balachander Krishnamurthy, Jia Wang, Yinglian Xie I. INTRODUCTION Peer-to-peer applications such as Napster [4], Freenet [1], and Gnutella
More informationDistributed Systems. Characteristics of Distributed Systems. Lecture Notes 1 Basic Concepts. Operating Systems. Anand Tripathi
1 Lecture Notes 1 Basic Concepts Anand Tripathi CSci 8980 Operating Systems Anand Tripathi CSci 8980 1 Distributed Systems A set of computers (hosts or nodes) connected through a communication network.
More informationDistributed Systems. Characteristics of Distributed Systems. Characteristics of Distributed Systems. Goals in Distributed System Designs
1 Anand Tripathi CSci 8980 Operating Systems Lecture Notes 1 Basic Concepts Distributed Systems A set of computers (hosts or nodes) connected through a communication network. Nodes may have different speeds
More informationSlides for Chapter 10: Peer-to-Peer Systems. From Coulouris, Dollimore, Kindberg and Blair Distributed Systems: Concepts and Design
Slides for Chapter 10: Peer-to-Peer Systems From Coulouris, Dollimore, Kindberg and Blair Distributed Systems: Concepts and Design Edition 5, Addison-Wesley 2012 Edited and supplemented by Jonne Itkonen,!
More informationMotivation for peer-to-peer
Peer-to-peer systems INF 5040 autumn 2015 lecturer: Roman Vitenberg INF5040, Frank Eliassen & Roman Vitenberg 1 Motivation for peer-to-peer Ø Inherent restrictions of the standard client/ server model
More informationPERFORMANCE ANALYSIS OF R/KADEMLIA, PASTRY AND BAMBOO USING RECURSIVE ROUTING IN MOBILE NETWORKS
International Journal of Computer Networks & Communications (IJCNC) Vol.9, No.5, September 27 PERFORMANCE ANALYSIS OF R/KADEMLIA, PASTRY AND BAMBOO USING RECURSIVE ROUTING IN MOBILE NETWORKS Farida Chowdhury
More informationResilient GIA. Keywords-component; GIA; peer to peer; Resilient; Unstructured; Voting Algorithm
Rusheel Jain 1 Computer Science & Information Systems Department BITS Pilani, Hyderabad Campus Hyderabad, A.P. (INDIA) F2008901@bits-hyderabad.ac.in Chittaranjan Hota 2 Computer Science & Information Systems
More informationA WebRTC DHT. Andres Ledesma (UCY) in cooperation with Mikael (Peerialism).
A WebRTC DHT Andres Ledesma (UCY) in cooperation with Mikael (Peerialism). Preface I Existing DHT overlays have been optimized using one criteria (network proximity, social links, content caching or others).
More informationPeerfactSim.KOM: A Simulation Framework for Peer-to-Peer Systems
PeerfactSim.KOM: A Simulation Framework for Peer-to-Peer Systems The 2011 International Conference on High Performance Computing & Simulation July 4 8, 2011, Istanbul, Turkey Dominik Stingl Christian Gross
More informationIntroduction to P2P Computing
Introduction to P2P Computing Nicola Dragoni Embedded Systems Engineering DTU Compute 1. Introduction A. Peer-to-Peer vs. Client/Server B. Overlay Networks 2. Common Topologies 3. Data Location 4. Gnutella
More informationCooperation in Open Distributed Systems. Stefan Schmid
Cooperation in Open Distributed Systems Stefan Schmid T-Labs, Berlin, July 2, 2009 Distributed Systems 2008/9 Wireless: Many mobile phones today have WLAN (and even Skype) P2P: Olympic games 2008 live-broadcast
More informationDistributed Hash Tables: Chord
Distributed Hash Tables: Chord Brad Karp (with many slides contributed by Robert Morris) UCL Computer Science CS M038 / GZ06 12 th February 2016 Today: DHTs, P2P Distributed Hash Tables: a building block
More informationWinter CS454/ Assignment 2 Instructor: Bernard Wong Due date: March 12 15, 2012 Group size: 2
Winter CS454/654 2012 Assignment 2 Instructor: Bernard Wong Due date: March 12 15, 2012 Group size: 2 Distributed systems is a rapidly evolving field. Most of the systems we have studied (or will study)
More informationEARM: An Efficient and Adaptive File Replication with Consistency Maintenance in P2P Systems.
: An Efficient and Adaptive File Replication with Consistency Maintenance in P2P Systems. 1 K.V.K.Chaitanya, 2 Smt. S.Vasundra, M,Tech., (Ph.D), 1 M.Tech (Computer Science), 2 Associate Professor, Department
More informationStructured Peer-to-Peer Networks
Structured Peer-to-Peer Networks The P2P Scaling Problem Unstructured P2P Revisited Distributed Indexing Fundamentals of Distributed Hash Tables DHT Algorithms Chord Pastry Can Programming a DHT Graphics
More informationSubway : Peer-To-Peer Clustering of Clients for Web Proxy
Subway : Peer-To-Peer Clustering of Clients for Web Proxy Kyungbaek Kim and Daeyeon Park Department of Electrical Engineering & Computer Science, Division of Electrical Engineering, Korea Advanced Institute
More informationOverlay and P2P Networks. Introduction and unstructured networks. Prof. Sasu Tarkoma
Overlay and P2P Networks Introduction and unstructured networks Prof. Sasu Tarkoma 14.1.2013 Contents Overlay networks and intro to networking Unstructured networks Overlay Networks An overlay network
More informationTime-related replication for p2p storage system
Seventh International Conference on Networking Time-related replication for p2p storage system Kyungbaek Kim E-mail: University of California, Irvine Computer Science-Systems 3204 Donald Bren Hall, Irvine,
More informationEfficient Resource Management for the P2P Web Caching
Efficient Resource Management for the P2P Web Caching Kyungbaek Kim and Daeyeon Park Department of Electrical Engineering & Computer Science, Division of Electrical Engineering, Korea Advanced Institute
More informationKademlia: A peer-to peer information system based on XOR. based on XOR Metric,by P. Maymounkov and D. Mazieres
: A peer-to peer information system based on XOR Metric,by P. Maymounkov and D. Mazieres March 10, 2009 : A peer-to peer information system based on XOR Features From past p2p experiences, it has been
More informationSaarland University Faculty of Natural Sciences and Technology I Department of Computer Science. Masters Thesis
Saarland University Faculty of Natural Sciences and Technology I Department of Computer Science Masters Thesis Experimental Comparison of Byzantine Fault Tolerant Distributed Hash Tables submitted by Supriti
More informationTelematics Chapter 9: Peer-to-Peer Networks
Telematics Chapter 9: Peer-to-Peer Networks Beispielbild User watching video clip Server with video clips Application Layer Presentation Layer Application Layer Presentation Layer Session Layer Session
More informationOverlay and P2P Networks. Unstructured networks. PhD. Samu Varjonen
Overlay and P2P Networks Unstructured networks PhD. Samu Varjonen 25.1.2016 Contents Unstructured networks Last week Napster Skype This week: Gnutella BitTorrent P2P Index It is crucial to be able to find
More informationPeer to Peer Systems and Probabilistic Protocols
Distributed Systems 600.437 Peer to Peer Systems & Probabilistic Protocols Department of Computer Science The Johns Hopkins University 1 Peer to Peer Systems and Probabilistic Protocols Lecture 11 Good
More informationApplication Layer Multicast For Efficient Peer-to-Peer Applications
Application Layer Multicast For Efficient Peer-to-Peer Applications Adam Wierzbicki 1 e-mail: adamw@icm.edu.pl Robert Szczepaniak 1 Marcin Buszka 1 1 Polish-Japanese Institute of Information Technology
More informationFaster Content Access in KAD
Faster Content Access in KAD Moritz Steiner, Damiano Carra, and Ernst W. Biersack Eurécom, Sophia Antipolis, France {steiner carra erbi}@eurecom.fr Abstract Many different Distributed Hash Tables (DHTs)
More informationAn Agenda for Robust Peer-to-Peer Storage
An Agenda for Robust Peer-to-Peer Storage Rodrigo Rodrigues Massachusetts Institute of Technology rodrigo@lcs.mit.edu Abstract Robust, large-scale storage is one of the main applications of DHTs and a
More informationData Replication under Latency Constraints Siu Kee Kate Ho
Data Replication under Latency Constraints Siu Kee Kate Ho (siho@cs.brown.edu) Abstract To maintain good quality of service, data providers have to satisfy requests within some specified amount of time.
More informationShaking Service Requests in Peer-to-Peer Video Systems
Service in Peer-to-Peer Video Systems Ying Cai Ashwin Natarajan Johnny Wong Department of Computer Science Iowa State University Ames, IA 500, U. S. A. E-mail: {yingcai, ashwin, wong@cs.iastate.edu Abstract
More informationRouting Table Construction Method Solely Based on Query Flows for Structured Overlays
Routing Table Construction Method Solely Based on Query Flows for Structured Overlays Yasuhiro Ando, Hiroya Nagao, Takehiro Miyao and Kazuyuki Shudo Tokyo Institute of Technology Abstract In structured
More informationSecure Distributed Storage in Peer-to-peer networks
Secure Distributed Storage in Peer-to-peer networks Øyvind Hanssen 07.02.2007 Motivation Mobile and ubiquitous computing Persistent information in untrusted networks Sharing of storage and information
More informationCompSci 356: Computer Network Architectures Lecture 21: Overlay Networks Chap 9.4. Xiaowei Yang
CompSci 356: Computer Network Architectures Lecture 21: Overlay Networks Chap 9.4 Xiaowei Yang xwy@cs.duke.edu Overview Problem Evolving solutions IP multicast Proxy caching Content distribution networks
More informationOverlay and P2P Networks. Introduction. Prof. Sasu Tarkoma
Overlay and P2P Networks Introduction Prof. Sasu Tarkoma 12.1.2015 Contents Course Overview Lectures Assignments/Exercises Course Overview Overlay networks and peer-to-peer technologies have become key
More informationIMPLEMENTING P2P RESOURCE SHARING APPLICATIONS IN WIRELESS MESH NETWORKS
IMPLEMENTING P2P RESOURCE SHARING APPLICATIONS IN WIRELESS MESH NETWORKS Dr.N.Kumareshan 1, Mr.N.Prakash 2 2 Assistant Professor (SG), 2 Assistant Professor 1,2 Department of ECE, 1 Sri Shakthi Institute
More informationCPSC 426/526. P2P Lookup Service. Ennan Zhai. Computer Science Department Yale University
CPSC 4/5 PP Lookup Service Ennan Zhai Computer Science Department Yale University Recall: Lec- Network basics: - OSI model and how Internet works - Socket APIs red PP network (Gnutella, KaZaA, etc.) UseNet
More informationOverlay and P2P Networks. Introduction. Prof. Sasu Tarkoma
Overlay and P2P Networks Introduction Prof. Sasu Tarkoma 13.1.2014 Contents Course Overview Lectures Assignments/Exercises Course Overview Overlay networks and peer-to-peer technologies have become key
More informationOverlay and P2P Networks. Unstructured networks. Prof. Sasu Tarkoma
Overlay and P2P Networks Unstructured networks Prof. Sasu Tarkoma 20.1.2014 Contents P2P index revisited Unstructured networks Gnutella Bloom filters BitTorrent Freenet Summary of unstructured networks
More informationA Scalable Content- Addressable Network
A Scalable Content- Addressable Network In Proceedings of ACM SIGCOMM 2001 S. Ratnasamy, P. Francis, M. Handley, R. Karp, S. Shenker Presented by L.G. Alex Sung 9th March 2005 for CS856 1 Outline CAN basics
More informationCS514: Intermediate Course in Computer Systems
Distributed Hash Tables (DHT) Overview and Issues Paul Francis CS514: Intermediate Course in Computer Systems Lecture 26: Nov 19, 2003 Distributed Hash Tables (DHT): Overview and Issues What is a Distributed
More informationFault Resilience of Structured P2P Systems
Fault Resilience of Structured P2P Systems Zhiyu Liu 1, Guihai Chen 1, Chunfeng Yuan 1, Sanglu Lu 1, and Chengzhong Xu 2 1 National Laboratory of Novel Software Technology, Nanjing University, China 2
More informationSelf-Correcting Broadcast in Distributed Hash Tables
Self-Correcting Broadcast in Distributed Hash Tables Ali Ghsi 1,Luc Onana Alima 1, Sameh El-Ansary 2, Per Brand 2 and Seif Haridi 1 1 IMIT-Royal Institute of Technology, Kista, Sweden 2 Swedish Institute
More information